Training in progress, epoch 3

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f88cec87344ef465a59d9c7a5cadea80a0ca757ab78dc39534c8acb833b16f1
+oid sha256:bde964023bc2d0c2ef9a56dcb662274beac2f80237b7f7c7848c18c8178223fe
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c64996222aec5b146bc58e3684f0bbc98a8cccbdcf82f21d52d7c8f857058eb3
+oid sha256:4d72d097dcd13abeaaa534a08fa18e0be7a8a7b811a3e3a52dab8899702a25ee
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2ae7799420b979b12dea4d8533831858d1cca0a3221119f11d60026c698fc0f
+oid sha256:042aa73788afe49f9f04c030812ef6332a35d688d9b51d7898768a3b70339d50
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bb62267c55f182fd258a9aad035a810b4f95c2c7b4c0eed751a72dc7c060c72
+oid sha256:e698240d6fba6470902b3882a63a87a27adca60c65166c40a4c2ced364778cdd
 size 1168138808

trainer_log.jsonl

@@ -62,3 +62,26 @@
 {"current_steps": 600, "total_steps": 834, "loss": 0.7163, "lr": 5e-06, "epoch": 2.158273381294964, "percentage": 71.94, "elapsed_time": "1:05:22", "remaining_time": "0:25:29"}
 {"current_steps": 610, "total_steps": 834, "loss": 0.7197, "lr": 5e-06, "epoch": 2.194244604316547, "percentage": 73.14, "elapsed_time": "1:06:25", "remaining_time": "0:24:23"}
 {"current_steps": 620, "total_steps": 834, "loss": 0.7192, "lr": 5e-06, "epoch": 2.2302158273381294, "percentage": 74.34, "elapsed_time": "1:07:27", "remaining_time": "0:23:17"}
+{"current_steps": 630, "total_steps": 834, "loss": 0.717, "lr": 5e-06, "epoch": 2.2661870503597124, "percentage": 75.54, "elapsed_time": "1:08:29", "remaining_time": "0:22:10"}
+{"current_steps": 640, "total_steps": 834, "loss": 0.7171, "lr": 5e-06, "epoch": 2.302158273381295, "percentage": 76.74, "elapsed_time": "1:09:31", "remaining_time": "0:21:04"}
+{"current_steps": 650, "total_steps": 834, "loss": 0.7179, "lr": 5e-06, "epoch": 2.338129496402878, "percentage": 77.94, "elapsed_time": "1:10:32", "remaining_time": "0:19:58"}
+{"current_steps": 660, "total_steps": 834, "loss": 0.7208, "lr": 5e-06, "epoch": 2.3741007194244603, "percentage": 79.14, "elapsed_time": "1:11:34", "remaining_time": "0:18:52"}
+{"current_steps": 670, "total_steps": 834, "loss": 0.7201, "lr": 5e-06, "epoch": 2.4100719424460433, "percentage": 80.34, "elapsed_time": "1:12:36", "remaining_time": "0:17:46"}
+{"current_steps": 680, "total_steps": 834, "loss": 0.7165, "lr": 5e-06, "epoch": 2.446043165467626, "percentage": 81.53, "elapsed_time": "1:13:38", "remaining_time": "0:16:40"}
+{"current_steps": 690, "total_steps": 834, "loss": 0.7199, "lr": 5e-06, "epoch": 2.4820143884892087, "percentage": 82.73, "elapsed_time": "1:14:39", "remaining_time": "0:15:34"}
+{"current_steps": 700, "total_steps": 834, "loss": 0.7228, "lr": 5e-06, "epoch": 2.5179856115107913, "percentage": 83.93, "elapsed_time": "1:15:41", "remaining_time": "0:14:29"}
+{"current_steps": 710, "total_steps": 834, "loss": 0.7211, "lr": 5e-06, "epoch": 2.553956834532374, "percentage": 85.13, "elapsed_time": "1:16:42", "remaining_time": "0:13:23"}
+{"current_steps": 720, "total_steps": 834, "loss": 0.7192, "lr": 5e-06, "epoch": 2.5899280575539567, "percentage": 86.33, "elapsed_time": "1:17:44", "remaining_time": "0:12:18"}
+{"current_steps": 730, "total_steps": 834, "loss": 0.7208, "lr": 5e-06, "epoch": 2.6258992805755397, "percentage": 87.53, "elapsed_time": "1:18:45", "remaining_time": "0:11:13"}
+{"current_steps": 740, "total_steps": 834, "loss": 0.7184, "lr": 5e-06, "epoch": 2.661870503597122, "percentage": 88.73, "elapsed_time": "1:19:46", "remaining_time": "0:10:08"}
+{"current_steps": 750, "total_steps": 834, "loss": 0.7139, "lr": 5e-06, "epoch": 2.697841726618705, "percentage": 89.93, "elapsed_time": "1:20:48", "remaining_time": "0:09:03"}
+{"current_steps": 760, "total_steps": 834, "loss": 0.7207, "lr": 5e-06, "epoch": 2.7338129496402876, "percentage": 91.13, "elapsed_time": "1:21:49", "remaining_time": "0:07:58"}
+{"current_steps": 770, "total_steps": 834, "loss": 0.7193, "lr": 5e-06, "epoch": 2.7697841726618706, "percentage": 92.33, "elapsed_time": "1:22:51", "remaining_time": "0:06:53"}
+{"current_steps": 780, "total_steps": 834, "loss": 0.7185, "lr": 5e-06, "epoch": 2.805755395683453, "percentage": 93.53, "elapsed_time": "1:23:53", "remaining_time": "0:05:48"}
+{"current_steps": 790, "total_steps": 834, "loss": 0.7217, "lr": 5e-06, "epoch": 2.841726618705036, "percentage": 94.72, "elapsed_time": "1:24:54", "remaining_time": "0:04:43"}
+{"current_steps": 800, "total_steps": 834, "loss": 0.7213, "lr": 5e-06, "epoch": 2.8776978417266186, "percentage": 95.92, "elapsed_time": "1:25:55", "remaining_time": "0:03:39"}
+{"current_steps": 810, "total_steps": 834, "loss": 0.7183, "lr": 5e-06, "epoch": 2.9136690647482015, "percentage": 97.12, "elapsed_time": "1:26:57", "remaining_time": "0:02:34"}
+{"current_steps": 820, "total_steps": 834, "loss": 0.7216, "lr": 5e-06, "epoch": 2.949640287769784, "percentage": 98.32, "elapsed_time": "1:27:58", "remaining_time": "0:01:30"}
+{"current_steps": 830, "total_steps": 834, "loss": 0.7198, "lr": 5e-06, "epoch": 2.985611510791367, "percentage": 99.52, "elapsed_time": "1:29:01", "remaining_time": "0:00:25"}
+{"current_steps": 834, "total_steps": 834, "eval_loss": 0.7752296328544617, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:31:23", "remaining_time": "0:00:00"}
+{"current_steps": 834, "total_steps": 834, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:32:50", "remaining_time": "0:00:00"}